VECTOR WIREAI INTELLIGENCE
NVDA$1,847+3.2%MSFT$512+1.1%GOOGL$199-0.4%META$728+2.7%AMD$184-1.2%TSM$212+0.6%PLTR$98+4.1%AI IDX4,821+1.9%
PKT
SEEDRefresh Models Deals Regulatory Sources

Kimi K2 (Reasoning) vs o4-mini

MoonshotvsOpenAI28 shared benchmarks208 head-to-head
BenchmarkKimi K2 (Reasoning)o4-mini
AA Agentic Index47.936.1
AA Intelligence33.526.1
AA-LCR70.360
AA-Omniscience-21.4-35.7
aider_polyglot59.172
AIME 202594.592.7
Artificial Analysis Coding Index34.825.6
browsecomp60.251.5
critpt2.60.6
frontiermath_tier_406.3
gdpval24.525.4
GPQA Diamond84.581.4
HLE23.916.5
IFBench68.168.7
LiveCodeBench79.284.5
multichallenge66.444.9
OmniScience Accuracy30.924.8
OmniScience Non-Hallucination25.819.5
scicode44.846.5
simplebench39.638.7
swe_bench_bash63.445
SWE-bench Verified71.368.1
Terminal-Bench Hard31.115.2
vectara_answer_rate98.699.2
vectara_avg_summary_length59.2130.9
vectara_factual_consistency82.181.4
vectara_hallucination_rate17.918.6
τ²-Bench Telecom (AA run)9355.6

Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.